Joanna Joiner , Zachary Fasnacht , Wenhan Qin , Yasuko Yoshida , Alexander Vasilkov, Can Li, Lok Lamsal, Nickolay Krotkov 

Space-based quantitative passive optical remote sensing of the Earth's surface typically involves the detection and elimination of cloud-contaminated pixels as an initial processing step. We explore a fundamentally different approach; we use machine learning with cloud contaminated satellite multi-spectral data to estimate underlying terrestrial surface reflectances at red, green, and blue (RGB) wavelengths. The NN reproduces land RGB reflectances with high fidelity even in scenes with moderate to high cloud optical thicknesses. This implies that spectral features of the Earth's surface can be detected and distinguished in the presence of clouds, even when they are partially obscured by clouds; the NN is able to separate the spectral fingerprint of the Earth's surface from that of the clouds, aerosols, gaseous absorption, and Rayleigh scattering, provided that there are adequately different spectral features and that the clouds are not completely opaque. Once trained, the NN enables rapid estimates of RGB reflectances with little computational cost. Aside from the training data, there is no requirement of prior information regarding the land surface spectral reflectance, nor is there need for radiative transfer calculations. We test different wavelength windows for reconstruction of surface reflectance. This work provides an initial example of a general approach that has many potential applications in land and ocean remote sensing as well as other practical uses such as in search and rescue, precision agriculture, and change detection.